No module named 'batchfold'?

[Amelie-Schreiber]

Issue with notebook:

On Generating New Protein Binders with RFDiffusion, ProteinMPNN, and ESMFold

I am trying to run the notebook as a colab instance. It would be helpful to have notebooks already setup with colab links. Sometimes running locally is difficult. I have the following notebook-requirements.txt file saved in my colab directory:

pip 
boto3==1.24.89 
matplotlib==3.6.1 
sagemaker==2.112.1 
botocore==1.27.89 
jaxlib==0.3.20
jax==0.3.21 
biopython==1.79 
py3Dmol==2.0.1.post1
dm-tree==0.1.7 
numpy==1.23.3 
attrs==22.1.0

The Problem

When running

%pip install -q -U -r notebook-requirements.txt

I get:

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
chex 0.1.7 requires jax>=0.4.6, but you have jax 0.3.21 which is incompatible.
flax 0.7.2 requires jax>=0.4.2, but you have jax 0.3.21 which is incompatible.
jsonschema 4.19.0 requires attrs>=22.2.0, but you have attrs 22.1.0 which is incompatible.
orbax-checkpoint 0.3.4 requires jax>=0.4.9, but you have jax 0.3.21 which is incompatible.
referencing 0.30.2 requires attrs>=22.2.0, but you have attrs 22.1.0 which is incompatible.
seaborn 0.12.2 requires matplotlib!=3.6.1,>=3.1, but you have matplotlib 3.6.1 which is incompatible.

Also, when running

import boto3
from batchfold.batchfold_environment import BatchFoldEnvironment
from batchfold.rfdiffusion_job import RFDiffusionJob
from batchfold.proteinmpnn_job import ProteinMPNNJob
from batchfold.batchfold_target import BatchFoldTarget
from batchfold.esmfold_job import ESMFoldJob
from batchfold.utils import utils
from datetime import datetime
import os
import py3Dmol
import json
import time
from math import ceil

boto_session = boto3.session.Session()
s3 = boto_session.client("s3")
batch_environment = BatchFoldEnvironment(boto_session=boto_session)

S3_BUCKET = batch_environment.default_bucket
S3_PREFIX = "binder-experiment-" + datetime.now().strftime("%Y%m%d%s")
S3_PATH = os.path.join("s3://", S3_BUCKET, S3_PREFIX)
JOB_QUEUE = "G4dnJobQueue"
print(f"S3 path is {S3_PATH}")
input_filename = "insulin_target.pdb"

I get:

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
[<ipython-input-3-f109ed0157f9>](https://localhost:8080/#) in <cell line: 2>()
      1 import boto3
----> 2 from batchfold.batchfold_environment import BatchFoldEnvironment
      3 from batchfold.rfdiffusion_job import RFDiffusionJob
      4 from batchfold.proteinmpnn_job import ProteinMPNNJob
      5 from batchfold.batchfold_target import BatchFoldTarget

ModuleNotFoundError: No module named 'batchfold'

---------------------------------------------------------------------------